Sound Event Detection with Adaptive Frequency Selection
arXiv:2105.07596
Abstract
In this work, we present HIDACT, a novel network architecture for adaptive computation for efficiently recognizing acoustic events. We evaluate the model on a sound event detection task where we train it to adaptively process frequency bands. The model learns to adapt to the input without requesting all frequency sub-bands provided. It can make confident predictions within fewer processing steps, hence reducing the amount of computation. Experimental results show that HIDACT has comparable performance to baseline models with more parameters and higher computational complexity. Furthermore, the model can adjust the amount of computation based on the data and computational budget.
arXiv commentAccepted by IEEE Workshop on Applications of Signal Processing to Audio and Acoustics 2021
References in corpus (6)
- Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
- Adaptive Computation Time for Recurrent Neural Networks
- PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
- The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation
- Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
- Ultra-Lightweight Speech Separation via Group Communication